An Explainer for Temporal Graph Neural Networks
This work addresses the problem of model transparency and trustworthiness for users of TGNNs in domains like transportation, though it appears incremental as it builds on existing explanation methods for temporal graphs.
The paper tackles the challenge of explaining temporal graph neural networks (TGNNs) by proposing a novel explainer framework that identifies dominant explanations as probabilistic graphical models over time periods, with case studies in transportation demonstrating its ability to discover dynamic dependency structures in road networks.
Temporal graph neural networks (TGNNs) have been widely used for modeling time-evolving graph-related tasks due to their ability to capture both graph topology dependency and non-linear temporal dynamic. The explanation of TGNNs is of vital importance for a transparent and trustworthy model. However, the complex topology structure and temporal dependency make explaining TGNN models very challenging. In this paper, we propose a novel explainer framework for TGNN models. Given a time series on a graph to be explained, the framework can identify dominant explanations in the form of a probabilistic graphical model in a time period. Case studies on the transportation domain demonstrate that the proposed approach can discover dynamic dependency structures in a road network for a time period.